X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=lustre%2FChangeLog;h=f461787c8e92a984b4daf5c4d6f0f9a90fbcd603;hp=66fd419eb24b3cca7524e479820308813b4b67d1;hb=cff450108c604eebd211e719007800539b537a61;hpb=d8d8fd9192a54c7b8caef8cca9b7a1eb5e5e3298 diff --git a/lustre/ChangeLog b/lustre/ChangeLog index 66fd419..f461787 100644 --- a/lustre/ChangeLog +++ b/lustre/ChangeLog @@ -1,8 +1,8 @@ tbd Sun Microsystems, Inc. * version 2.0.0 * Support for kernels: - 2.6.16.60-0.27 (SLES 10), - 2.6.18-92.1.10.el5 (RHEL 5), + 2.6.16.60-0.33 (SLES 10), + 2.6.18-92.1.22.el5 (RHEL 5), 2.6.22.14 vanilla (kernel.org). * Client support for unpatched kernels: (see http://wiki.lustre.org/index.php?title=Patchless_Client) @@ -13,6 +13,146 @@ tbd Sun Microsystems, Inc. removed cwd "./" (refer to Bugzilla 14399). * File join has been disabled in this release, refer to Bugzilla 16929. +Severity : normal +Frequency : normal +Bugzilla : 12069 +Descriptoin: OST grant too much space to client even there are not enough space. +Details : Client will shrink its grant cache to OST if there are no write + activity over 6 mins (GRANT_SHRINK_INTERVAL), and OST will retrieve + this grant cache if there are already not enough avaible space + (left_space < total_clients * 32M). + +Severity : normal +Frequency : start MDS on uncleanly shutdowned MDS device +Bugzilla : 16839 +Descriptoin: ll_sync thread stay in waiting mds<>ost recovery finished +Details : stay in waiting mds<>ost recovery finished produce random bugs + due race between two ll_sync thread for one lov target. send + ACTIVATE event only if connect realy finished and import have + FULL state. + +Severity : normal +Frequency : rare, connect and disconnect target at same time +Bugzilla : 17310 +Descriptoin: ASSERTION(atomic_read(&imp->imp_inflight) == 0 +Details : don't call obd_disconnect under lov_lock. this long time + operation and can block ptlrpcd which answer to connect request. + +Severity : normal +Frequency : rare +Bugzilla : 18154 +Descriptoin: don't lose wakeup for imp_recovery_waitq +Details : recover_import_no_retry or invalidate_import and import_close can + both sleep on imp_recovery_waitq, but we was send only one wakeup + to sleep queue. + +Severity : normal +Frequency : always with long access acl +Bugzilla : 17636 +Descriptoin: mds can't pack reply with long acl. +Details : mds don't control size of acl but they limited by reint/getattr + reply buffer. + +Severity : enhancement +Bugzilla : 18061 +Description: Update to SLES10 kernel-2.6.16.60-0.33. + +Severity : enhancement +Bugzilla : 18060 +Description: Update to RHEL5 kernel-2.6.18-92.1.22.el5. + +Severity : normal +Frequency : start MDS on uncleanly shutdowned MDS device +Bugzilla : 18049 +Descriptoin: aborting recovery hang on MDS +Details : don't throttle destroy RPCs for the MDT. + +Severity : major +Frequency : on remount +Bugzilla : 18018 +Description: external journal device not working after the remount +Details : clear dev_rdonly flag for external journal devices in + blkdev_put() + +Severity : minor +Frequency : rare +Bugzilla : 17802 +Description: shutdown vs evict race +Details : client_disconnect_export vs connect request race. + if client will evicted at this time - we start invalidate + thread without referece to import and import can be freed + at same time. + +Severity : normal +Frequency : rare, need acl's on inode. +Bugzilla : 16492 +Description: client can't handle ost additional correctly +Details : if ost was added after client connected to mds client can have + hit lnet_try_match_md ... to big messages to wide striped files. + in this case need teach client to handle config events about add + lov target and update client max ea size at that event. + +Severity : enhancement +Bugzilla : 15699 +Description: Changelogs +Details : Changelogs are a lightweight mechanism to track filesystem + metadata and namespace changes. The changelog is recorded + permanently on the MDTs, and is periodically "consumed" / purged + when records are no longer needed. + +Severity : enhancement +Bugzilla : 15957 +Description: compact fld format with extents +Details : Store range of seq rather than every seq in FLD. Seq + controller update FLD rather than clients. In Case of CMD, mdt0 + has FLD, all other metadata server act as non persistent proxy + for FLD queries and cache fld entries in fld cache. + +Severity : normal +Frequency : rare +Bugzilla : 16081 +Description: don't skip ost target if they assigned to file +Details : Drop slow OSCs if we can, but not for requested start idx. + This means "if OSC is slow and it is not the requested + start OST, then it can be skipped, otherwise skip it only + if it is inactive/recovering/out-of-space. + +Severity : normal +Bugzilla : 16080 +Description: more cleanup in mds_lov +Details : not send LOV EA under replay, we can't know about they size at this + time. Don't allow client connect to mds before any ost connected, + for avoid problems with LOV EA size and returning EIO to client. + +Severity : enhancement +Bugzilla : 11826 +Description: Interoperability at server side (Disk interoperability) + +Severity : enhancement +Bugzilla : 17201 +Description: Update to RHEL5 kernel-2.6.18-92.1.17.el5. + +Severity : enhancement +Bugzilla : 17458 +Description: Update to SLES10 SP2 kernel-2.6.16.60-0.31. + +Severity : enhancement +Bugzilla : 14166 +Description: New client IO stack (CLIO). + +Severity : enhancement +Bugzilla : 15393 +Description: Commit on sharing. Eliminate inter-client dependencies between + uncommitted transactions by doing transaction commits. + Thereby clients may recovery independently. + +Severity : normal +Frequency : Create a symlink file with a very long name +Bugzilla : 16578 +Description: ldlm_cancel_pack()) ASSERTION(max >= dlm->lock_count + count) +Details : If there is no extra space in the request for early cancels, + ldlm_req_handles_avail() returns 0 instead of a negative value. + Severity : enhancement Bugzilla : 1819 Description: Add /proc entry for import status @@ -45,6 +185,15 @@ Description: Hitting mdc_commit_close() ASSERTION Details : Properly handle request reference release in ll_release_openhandle(). +Severity : major +Bugzilla : 14840 +Description: quota recovery deadlock during mds failover +Details : This patch includes att18982, att18236, att18237 in bz14840. + Slove the problems: + 1. fix osts hang when mds does failover with quotaon + 2. prevent watchdog storm when osts threads wait for the + recovery of mds + Severity : normal Bugzilla : 15975 Frequency : only patchless client @@ -114,6 +263,7 @@ Details : When connection is reused this not moved from CONN_UNUSED_HASH into CONN_USED_HASH and this prodice warning when put connection again in unused hash. + Severity : enhancement Bugzilla : 15899 Description: File striping can now be set to use an arbitrary pool of OSTs. @@ -129,6 +279,23 @@ Details : Apply the MGS_CONNECT_SUPPORTED mask at reconnect time so the connect flags are properly negotiated. Severity : normal +Frequency : often +Bugzilla : 16125 +Description: quotas are not honored with O_DIRECT +Details : all writes with the flag O_DIRECT will use grants which leads to + this problem. Now using OBD_BRW_SYNC to guard this. + +Severity : normal +Bugzilla : 15058 +Description: add quota statistics +Details : 1. sort out quota proc entries and proc code. + 2. add quota statistics + +Severity : enhancement +Bugzilla : 13058 +Description: enable quota support for HEAD. + +Severity : normal Bugzilla : 16006 Description: Properly propagate oinfo flags from lov to osc for statfs Details : restore missing copy oi_flags to lov requests. @@ -1549,9 +1716,9 @@ Details : Kill unused ldlm_handle2lock_ns() function. Severity : normal Bugzilla : 16450 Description: Add lu_ref support to ldlm_lock -Details : lu_ref support for ldlm_lock and ldlm_resource. See lu_ref patch. - lu_ref fields ->l_reference and ->lr_reference are added to ldlm_lock - and ldlm_resource. LDLM interface has to be changed, because code that +Details : lu_ref support for ldlm_lock and ldlm_resource. See lu_ref patch. + lu_ref fields ->l_reference and ->lr_reference are added to ldlm_lock + and ldlm_resource. LDLM interface has to be changed, because code that releases a reference on a lock, has to "know" what reference this is. In the most frequent case @@ -1559,12 +1726,12 @@ Details : lu_ref support for ldlm_lock and ldlm_resource. See lu_ref patch. ... LDLM_LOCK_PUT(lock); - no changes are required. When any other reference (received _not_ from - ldlm_handle2lock()) is released, LDLM_LOCK_RELEASE() has to be called + no changes are required. When any other reference (received _not_ from + ldlm_handle2lock()) is released, LDLM_LOCK_RELEASE() has to be called instead of LDLM_LOCK_PUT(). Arguably, changes are pervasive, and interface requires some discipline - for proper use. On the other hand, it was very instrumental in finding + for proper use. On the other hand, it was very instrumental in finding a few leaked lock references. Severity : normal @@ -1577,7 +1744,7 @@ Details : Introduce ldlm_lock_addref_try() function (used by CLIO) that Severity : normal Bugzilla : 16450 Description: Add ldlm_weigh_callback(). -Details : Add new ->l_weigh_ast() call-back to ldlm_lock. It is called +Details : Add new ->l_weigh_ast() call-back to ldlm_lock. It is called by ldlm_cancel_shrink_policy() to estimate lock "value", instead of hard-coded `number of pages' logic. @@ -1617,8 +1784,8 @@ Details : Introduce new lu_context functions that are needed on the client Severity : normal Bugzilla : 16450 Description: Add start and stop methods to lu_device_type_operations. -Details : Introduce two new methods in lu_device_type_operations, that are - invoked when first instance of a given type is created and last one +Details : Introduce two new methods in lu_device_type_operations, that are + invoked when first instance of a given type is created and last one is destroyed respectively. This is need by CLIO. Severity : normal @@ -1663,7 +1830,7 @@ Severity : normal Bugzilla : 16450 Description: Introduce struct md_site and move meta-data specific parts of struct lu_site here. -Details : Move md-specific fields out of struct lu_site into special struct +Details : Move md-specific fields out of struct lu_site into special struct md_site, so that lu_site can be used on a client. Severity : minor @@ -1736,6 +1903,75 @@ Description: More exported tunables for mballoc Details : Add support for tunable preallocation window and new tunables for large/small requests +Severity : normal +Bugzilla : 16680 +Description: Detect corruption of block bitmap and checking for preallocations +Details : Checks validity of on-disk block bitmap. Also it does better + checking of number of applied preallocations. When corruption is + found, it turns filesystem readonly to prevent further corruptions. + +Severity : normal +Bugzilla : 17197 +Description: (rw.c:1323:ll_read_ahead_pages()) ASSERTION(page_idx > ria->ria_stoff) failed +Details : Once the unmatched stride IO mode is detected, shrink the stride-ahead + window to 0. If it does hit cache miss, and read-pattern is still + stride-io mode, does not reset the stride window, but also does not + increase the stride window length in this case. + +Severity : normal +Bugzilla : 16438 +Frequency : only for big-endian servers +Description: Check if system is big-endian while mounting fs with extents feature +Details : Mounting a filesystem with extents feature will fail on big-endian + systems since ext3-based ldiskfs is not supported on big-endian + systems. This can be over-riden with "bigendian_extents" mount option. + +Severity : enhancement +Bugzilla : 12749 +Description: The root squash functionality +Details : A security feature, which is to prevent users from being able + to mount lustre on their desktop, run as root, and delete + all of the files in the filesystem. The goal is accomplished by + remapping user id (UID) and group id (GID) of the root user to + a UID and GID specified by the system administartor via Lustre + configuration management server (MGS). The functionality also + allows to specify sets of clients for which the remapping does + not apply. + +Severity : normal +Bugzilla : 16860 +Description: Excessive recovery window +Details : With AT enabled, the recovery window can be excessively long (6000+ + seconds). To address this problem, we no longer use + OBD_RECOVERY_FACTOR when extending the recovery window (the connect + timeout no longer depends on the service time, it is set to + INITIAL_CONNECT_TIMEOUT now) and clients report the old service + time via pb_service_time. + +Severity : normal +Bugzilla : 16522 +Description: Watchdog triggered on MDS failover +Details : enable OBD_CONNECT_MDT flag when connecting from the MDS so that + the OSTs know that the MDS "UUID" can be reused for the same export + from a different NID, so we do not need to wait for the export to be + evicted + +Severity : major +Frequency : rare, only if using MMP with Linux RAID +Bugzilla : 17895 +Description: MMP doesn't work with Linux RAID +Details : While using HA for Lustre servers with Linux RAID, it is possible + that MMP will not detect multiple mounts. To make this work we + need to unplug the device queue in RAID when the MMP block is being + written. Also while reading the MMP block, we should read it from + disk and not the cached one. + +Severity : enhancement +Bugzilla : 17187 +Description: open file using fid +Details : A file can be opened using just its fid, like + /.lustre/fid/SEQ:OID:VER - this is needed for HSM and replication + -------------------------------------------------------------------------------- 2007-08-10 Cluster File Systems, Inc.